Ruay-Shiung Chang

Flooding-limited and multi-constrained QoS multicast routing based on the genetic algorithm for MANETs

A wireless MANET is a collection of wireless mobile hosts that dynamically create a temporary network without a fixed infrastructure. The topology of the network may change unpredictably and frequently. Therefore, multicast routing in ad hoc networks is a very challenging problem. This paper proposes a multi-constrained QoS multicast routing method using the genetic algorithm. The proposal will be flooding-limited using the available resources and minimum computation time in a dynamic environment. By selecting the appropriate values for parameters such as crossover, mutation, and population size, the genetic algorithm improves and tries to optimize the routes. Simulation results indicate its better performances compared to other methods.

A green energy-efficient scheduling algorithm using the DVFS technique for cloud datacenters

Abstract Information and communication technology (ICT) has a profound impact on environment because of its large amount of CO2 emissions. In the past years, the research field of “green” and low power consumption networking infrastructures is of great importance for both service/network providers and equipment manufacturers. An emerging technology called Cloud computing can increase the utilization and efficiency of hardware equipment. The job scheduler is needed by a cloud datacenter to arrange resources for executing jobs. In this paper, we propose a scheduling algorithm for the cloud datacenter with a dynamic voltage frequency scaling technique. Our scheduling algorithm can efficiently increase resource utilization; hence, it can decrease the energy consumption for executing jobs. Experimental results show that our scheme can reduce more energy consumption than other schemes do. The performance of executing jobs is not sacrificed in our scheme. We provide a green energy-efficient scheduling algorithm using the DVFS technique for Cloud computing datacenters.

The minimum labeling spanning trees

Abstract One of the fundamental problems in graph theory is to compute a minimum weight spanning tree. In this paper, a variant of spanning trees, called the minimum labeling spanning tree, is studied. The purpose is to find a spanning tree that tries to use edges that are as similar as possible. Giving each edge a label, the minimum labeling spanning tree is to find a spanning tree whose edge set consists of the smallest possible number of labels. This problem is shown to be NP-complete even for complete graphs. Two heuristic algorithms and an exact algorithm, based on the A ∗ - algorithm , are presented. According to the experimental results, one of the heuristic algorithms is very effective and the exact algorithm is very efficient.

Hybrid wireless network protocols

Basically, there are two types of wireless network systems - base-station (BS) oriented networks and ad hoc wireless networks. In the first type, the mobile hosts communicate with base stations, while, in ad hoc networks, the mobile hosts communicate with one another directly. The BS-oriented wireless network has better performance and is more reliable. However, the ad hoc network topology is desirable because of its low cost, plug-and-play convenience, and flexibility. Its usage of bandwidth and battery power is more efficient, but route and communication connectivity is fairly weak; any migration by a host participating in one or more routes could make the route invalid. Much cost is incurred in maintaining communication. Thus, the ad hoc wireless network is only suitable for applications in a small geographical area. We propose hybrid wireless network protocols to combine the advantages of BS-oriented and ad hoc wireless networks. We allow two mobile hosts to communicate directly (one-hop direct transmission) or through another mobile host (two-hop direct transmission) within a BS-oriented network. The hybrid protocols are more flexible, reliable, and have better performance than the traditional protocols. Simulation results show that two-hop direct-transmission has a lower non-completion probability. If the communicating parties are always within a two-hop direct-transmission area, the rate of complete communication improves by about 20%.

Improving job scheduling algorithms in a grid environment

Due to the advances in human civilization, problems in science and engineering are becoming more complicated than ever before. To solve these complicated problems, grid computing becomes a popular tool. A grid environment collects, integrates, and uses heterogeneous or homogeneous resources scattered around the globe by a high-speed network. A grid environment can be classified into two types: computing grids and data grids. This paper mainly focuses on computing grids. In computing grid, job scheduling is a very important task. A good scheduling algorithm can assign jobs to resources efficiently and can balance the system load. In this paper, we propose a hierarchical framework and a job scheduling algorithm called Hierarchical Load Balanced Algorithm (HLBA) for Grid environment. In our algorithm, we use the system load as a parameter in determining a balance threshold. And the scheduler adapts the balance threshold dynamically when the system load changes. The main contributions of this paper are twofold. First, the scheduling algorithm balances the system load with an adaptive threshold and second, it minimizes the makespan of jobs. Experimental results show that the performance of HLBA is better than those of other algorithms.

Self-Deployment by Density Control in Sensor Networks

Sensing coverage is an important issue in wireless mobile sensor networks. The strategy of how to deploy sensor nodes in an environment, particularly in an unknown expanse, will affect the utility of the network just like the quality of communication. In this paper, using the concept of molecule spreading from physics, we present an efficient method for sensor deployment, assuming that global information is not available. Our algorithm, i.e., Self-Deployment by Density Control (SDDC), uses density control by each node to concurrently deploy sensor nodes. We make the nodes form clusters to achieve area density balance. The characteristics in SDDC are concurrent multisensor moving, distributed operation, localized calculation, and self-deployment. Simulations show its good performances compared to the incremental self-deployment algorithm.

Adaptable Replica Consistency Service for Data Grids

In this paper, we focus our attentions on the replica consistency problems in data grids. An innovative and effective architecture called adaptable replica consistency service (ARCS) with the capability of dealing with the replica consistency is proposed. It can increase the performances and achieve load balancing for file replications in data grids. The model and experimental simulations are presented and evaluated by means of OptorSim as compared with the other two proposed coherence protocols. ARCS is superior to them as well as being suitable for the data grids environments according to our simulations results

Multicast ATM switches: survey and performance evaluation

Computer networks are undergoing a remarkable transformation. The widespread use of optical fiber to transmit data has made tremendous increases in network bandwidth. Furthermore, greater CPU power, increasing disk capacity, and support for digital audio and video are creating demand for a new class of network services. For example, video-on-demand, distant learning, distant diagnosis, video conferences, and many others applications have popped up one after another in recent years. Many of these services have one thing in common. They all require that the same piece of data be sent to multiple recipients. Even in traditional networks, this operation, called multicasting, can not be handled easily and cheaply. When scaled up to high speed ATM-based networks, the situation could be worse. Multiple streams of data travel around ATM networks. Each tries to send to many different destinations simultaneously. Therefore, designing economical ATM network switches which can support multicasting operations easily is very important in the future generation high speed networks. In the past twelve years or so, many designs for multicasting ATM switches are proposed. It seems about time to do a historical survey. It is hoped that by learning from the wisdom of the previous authors, new spark or angle can be found and exploited to design new multicasting ATM switches. Without easy and inexpensive multicasting, all the exciting services may become unaffordable. This will in turn lead to the diminishing of customer bases and finally will hinder the full-scale deployment of high speed networks.

Routing with adaptive path and limited flooding for mobile ad hoc networks

In MANET, each mobile host can freely move around and the network topology is dynamically constructed. To send a datagram, a source host broadcasts a route discovery packet to the network. All neighboring nodes receiving this packet will rebroadcast this packet until it reaches the destination. It will have large flooding overhead, poor network performance and undesirable battery power consumption. To improve network performance, we designed a novel routing protocol called RAPLF (routing with adaptive path and limited flooding) for mobile ad hoc networks. Simulation results showed that our protocol has better performance especially in packet delivery rate and flooding overhead when compared to similar protocols.

Handoff ordering using signal strength for multimedia communications in wireless networks

In this paper, we present a method for improving the quality of service (QoS) in multimedia wireless systems based on prioritization of handover requests. A strategy called signal strength for multimedia communications (SSMC) is proposed. In this strategy, we calculate a handoff priority for every multimedia service using three values: the static priority value, the degradation rate of the received signal strength (/spl Delta/RSS), and the RSS level itself. Then, each handoff request is queued and handled according to its priority value. We present the detailed algorithm and analyze its performance on a 25-cell network. Then, its performance is compared with other methods by simulations. The results indicate our method can effectively reduce the handoff call dropping probability compared to nonpriority schemes.